Rajiv Ratn Shah

Hierarchical local attention in TextNCA reveals that the arrangement of attention windows can dramatically influence language modeling performance, even more than the model's iterative nature.

InductWave achieves competitive logical query answering with half the message-passing layers, making it a game-changer for resource-constrained environments.

Targeted feedback can slash calculation errors in small language models from 56.9% to 23.5%, revolutionizing their physics reasoning abilities.

Code LLMs can recognize incorrect instructions but still follow them, leading to irrecoverable semantic errors that defy traditional evaluation metrics.

A comprehensive taxonomy reveals critical failure modes in LLM reasoning, exposing vulnerabilities that could hinder their deployment in real-world applications.

Scaling up LLMs doesn't uniformly improve context handling; instead, it paradoxically amplifies the tendency to copy irrelevant tokens while simultaneously improving resistance to misinformation.